remove html links from snippets; if <ul> is greater than </ul>'s count, add </ul> to snippet content

small-nav
Mimi Momo 4 years ago
parent 768a5da121
commit a24e8e8426

@ -1,4 +1,4 @@
import datetime, os
import datetime, os, re
from bottle import error, route, run, static_file, template
# make article-to-html work with entries
@ -25,17 +25,22 @@ def list_snippets(articles):
result = []
for article in articles:
path = 'entries/' + article
text = []
a = []
length = 0
with open('entries/feature/' + article) as f:
with open('entries/' + article) as f:
text = f.readlines()
length = len(text)
a.append(text[head])
a.append(snip_article(find_content(article, length, head, tail)))
content = snip_article(find_content(article, length, head, tail), path)
if content.count('<ul>') > content.count('</ul>'):
content += '</ul>'
a.append(content)
a.append(text[head + 1])
a.append("social")
a.append('entries/feature/' + article)
a.append(path)
result.append(a)
return result
@ -47,16 +52,22 @@ def count_lines(fname):
def find_content(article, length, head, tail):
content = ""
with open('entries/feature/' + article) as f:
with open('entries/' + article) as f:
for pos, line in enumerate(f):
if pos > head + 1 and pos < length - tail:
content += line
return content
def snip_article(article):
def clean(result, path):
result = result.replace('<br>','')
result = re.sub(r'<a href=.*?>', '', result)
result = result.replace('</a>','')
return result
def snip_article(article, path):
article = clean(article, path)
limit = 300
result = article[0:min(len(article),limit)]
result = result.replace('<br>','')
result = result.rsplit(' ',1)[0]
return result + " ... "
@ -65,7 +76,9 @@ def sort_files(files):
return files
def gather_files():
return os.listdir('entries/feature/')
files = os.listdir('entries/')
files.remove('raw')
return files
# Static

Loading…
Cancel
Save